{"id":"https://openalex.org/W4387969186","doi":"https://doi.org/10.1145/3581783.3612134","title":"Cuing Without Sharing: A Federated Cued Speech Recognition Framework via Mutual Knowledge Distillation","display_name":"Cuing Without Sharing: A Federated Cued Speech Recognition Framework via Mutual Knowledge Distillation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969186","doi":"https://doi.org/10.1145/3581783.3612134"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103126205","display_name":"Yuxuan Zhang","orcid":"https://orcid.org/0009-0006-4419-3184"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxuan Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059565360","display_name":"Lei Liu","orcid":"https://orcid.org/0000-0001-8109-5248"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418818","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-4497-0135"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103126205"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":1.2074,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80330212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8781","last_page":"8789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114463090896606},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.6654317378997803},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5444049835205078},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.48075124621391296},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46391525864601135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4390893578529358},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42078250646591187},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3475295603275299},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09711256623268127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114463090896606},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.6654317378997803},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5444049835205078},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.48075124621391296},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46391525864601135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4390893578529358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42078250646591187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3475295603275299},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09711256623268127},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1972680065","https://openalex.org/W2028778923","https://openalex.org/W2127141656","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2799813293","https://openalex.org/W2888888638","https://openalex.org/W2890863563","https://openalex.org/W2985525390","https://openalex.org/W2998687373","https://openalex.org/W3008402854","https://openalex.org/W3038022836","https://openalex.org/W3080411117","https://openalex.org/W3100760018","https://openalex.org/W3113399631","https://openalex.org/W3127299377","https://openalex.org/W3193972328","https://openalex.org/W3196371845","https://openalex.org/W3196826198","https://openalex.org/W3206845050","https://openalex.org/W4224224340","https://openalex.org/W4225685860","https://openalex.org/W4225978071","https://openalex.org/W4229022650","https://openalex.org/W4319586818","https://openalex.org/W6600512042","https://openalex.org/W6759238902"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Cued":[0,89],"Speech":[1,90],"(CS)":[2],"is":[3,115,148,160,183,208],"a":[4,86,110,130,143],"visual":[5,137,164,178],"coding":[6],"tool":[7],"to":[8,22,38,69,94,117,150,212],"encode":[9],"spoken":[10],"languages":[11],"at":[12],"the":[13,59,70,100,123,140,152,156,163,167,174,177,195,199,202,209,214,224],"phonetic":[14],"level,":[15],"which":[16,45,127,159],"combines":[17],"lip-reading":[18],"and":[19,49,74,136,241,256,267],"hand":[20],"gestures":[21],"effectively":[23],"assist":[24],"communication":[25],"among":[26],"people":[27],"with":[28,162,185,228],"hearing":[29],"impairments.":[30],"The":[31,263],"Automatic":[32],"CS":[33,40,78,102,125,226,265],"Recognition":[34,91],"(ACSR)":[35],"task":[36,217],"aims":[37],"recognize":[39],"videos":[41,76],"into":[42],"linguistic":[43,135,146,196],"texts,":[44],"involves":[46],"both":[47,236],"lips":[48],"hands":[50],"as":[51,198],"two":[52],"distinct":[53],"modalities":[54],"conveying":[55],"complementary":[56],"information.":[57,107,138],"However,":[58],"traditional":[60],"centralized":[61,243],"training":[62],"approach":[63,211,234],"poses":[64],"potential":[65],"privacy":[66,219],"risks":[67],"due":[68],"use":[71],"of":[72,122,180,204],"facial":[73],"gesture":[75],"in":[77,155],"data.":[79],"To":[80,201],"address":[81],"this":[82,207],"issue,":[83],"we":[84],"propose":[85],"new":[87],"Federated":[88],"(FedCSR)":[92],"framework":[93],"train":[95],"an":[96],"ACSR":[97,216,245],"model":[98,147,179,197],"over":[99],"decentralized":[101],"data":[103],"without":[104],"sharing":[105],"private":[106],"In":[108],"particular,":[109],"mutual":[111],"knowledge":[112],"distillation":[113,193],"method":[114],"proposed":[116],"maintain":[118],"cross-modal":[119],"semantic":[120],"consistency":[121],"Non-IID":[124],"data,":[126,189],"ensures":[128],"learning":[129,239],"unified":[131],"feature":[132],"space":[133],"for":[134,218,251,258],"On":[139,173],"server":[141],"side,":[142,176],"globally":[144],"shared":[145],"trained":[149,184],"capture":[151],"long-term":[153],"dependencies":[154],"text":[157],"sentences,":[158],"aligned":[161],"information":[165],"from":[166],"local":[168,188],"clients":[169],"via":[170],"visual-to-linguistic":[171],"distillation.":[172],"client":[175,182],"each":[181],"its":[186],"own":[187],"assisted":[190],"by":[191],"linguistic-to-visual":[192],"treating":[194],"teacher.":[200],"best":[203],"our":[205,233,268],"knowledge,":[206],"first":[210],"consider":[213],"federated":[215,238],"protection.":[220],"Experimental":[221],"results":[222],"on":[223],"Chinese":[225,264],"dataset":[227,266],"multiple":[229],"cuers":[230],"demonstrate":[231],"that":[232],"outperforms":[235],"mainstream":[237],"baselines":[240],"existing":[242],"state-of-the-art":[244],"methods,":[246],"achieving":[247],"9.7%":[248],"performance":[249],"improvement":[250],"character":[252],"error":[253,260],"rate":[254,261],"(CER)":[255],"15.0%":[257],"word":[259],"(WER).":[262],"code":[269],"will":[270],"be":[271],"open-sourced.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}